ClawHub
Back to skill

Security audit

Claude Code Memory

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, repo-local memory workflow with no executable code, network payloads, hidden persistence, or credential handling.

Install only if you want a local cross-session memory workflow. Review any .agent-memory/ or instruction-file changes before accepting them, and avoid saving secrets, credentials, regulated personal data, or sensitive user attributes in durable memory.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 94)May include surrounding context.

md
## Quick start

1. Put this repo in your skills directory
2. Create `.agent-memory/` in the target project
3. Map your rule layer to `CLAUDE.md`, `CLAUDE.local.md`, `AGENTS.md`, or another instruction file
4. Keep active work in `.agent-memory/session/summary.md`
5. Store reusable facts as indexed topic files under `.agent-memory/`

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The document explicitly recommends storing cross-session information about the user and collaboration guidance, but it does not define privacy boundaries, data minimization rules, or restrictions on sensitive personal data. In a memory-management skill, this omission can lead agents or operators to persist unnecessary personal or sensitive information across sessions, increasing privacy, compliance, and data-retention risk.

Content

No source excerpt is available for this finding.